Hugging Face's logo

smjain
/
sql-0

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files Metrics Community
sql-0
File size: 1,621 Bytes 
ae60608
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.69,
  "eval_steps": 500,
  "global_step": 1035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.6747,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001925925925925926,
      "loss": 0.4326,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.32,
      "step": 300
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.2383,
      "step": 400
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.1934,
      "step": 500
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.1729,
      "step": 600
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00011851851851851852,
      "loss": 0.1683,
      "step": 700
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001037037037037037,
      "loss": 0.1237,
      "step": 800
    },
    {
      "epoch": 2.42,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.1201,
      "step": 900
    },
    {
      "epoch": 2.62,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.1295,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 1500,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 8.401830279118848e+16,
  "trial_name": null,
  "trial_params": null
}